WSL2-Linux-Kernel/net/ipv6/sysctl_net_ipv6.c

304 строки
7.3 KiB
C
Исходник Обычный вид История

License cleanup: add SPDX GPL-2.0 license identifier to files with no license Many source files in the tree are missing licensing information, which makes it harder for compliance tools to determine the correct license. By default all files without license information are under the default license of the kernel, which is GPL version 2. Update the files which contain no license information with the 'GPL-2.0' SPDX license identifier. The SPDX identifier is a legally binding shorthand, which can be used instead of the full boiler plate text. This patch is based on work done by Thomas Gleixner and Kate Stewart and Philippe Ombredanne. How this work was done: Patches were generated and checked against linux-4.14-rc6 for a subset of the use cases: - file had no licensing information it it. - file was a */uapi/* one with no licensing information in it, - file was a */uapi/* one with existing licensing information, Further patches will be generated in subsequent months to fix up cases where non-standard license headers were used, and references to license had to be inferred by heuristics based on keywords. The analysis to determine which SPDX License Identifier to be applied to a file was done in a spreadsheet of side by side results from of the output of two independent scanners (ScanCode & Windriver) producing SPDX tag:value files created by Philippe Ombredanne. Philippe prepared the base worksheet, and did an initial spot review of a few 1000 files. The 4.13 kernel was the starting point of the analysis with 60,537 files assessed. Kate Stewart did a file by file comparison of the scanner results in the spreadsheet to determine which SPDX license identifier(s) to be applied to the file. She confirmed any determination that was not immediately clear with lawyers working with the Linux Foundation. Criteria used to select files for SPDX license identifier tagging was: - Files considered eligible had to be source code files. - Make and config files were included as candidates if they contained >5 lines of source - File already had some variant of a license header in it (even if <5 lines). All documentation files were explicitly excluded. The following heuristics were used to determine which SPDX license identifiers to apply. - when both scanners couldn't find any license traces, file was considered to have no license information in it, and the top level COPYING file license applied. For non */uapi/* files that summary was: SPDX license identifier # files ---------------------------------------------------|------- GPL-2.0 11139 and resulted in the first patch in this series. If that file was a */uapi/* path one, it was "GPL-2.0 WITH Linux-syscall-note" otherwise it was "GPL-2.0". Results of that was: SPDX license identifier # files ---------------------------------------------------|------- GPL-2.0 WITH Linux-syscall-note 930 and resulted in the second patch in this series. - if a file had some form of licensing information in it, and was one of the */uapi/* ones, it was denoted with the Linux-syscall-note if any GPL family license was found in the file or had no licensing in it (per prior point). Results summary: SPDX license identifier # files ---------------------------------------------------|------ GPL-2.0 WITH Linux-syscall-note 270 GPL-2.0+ WITH Linux-syscall-note 169 ((GPL-2.0 WITH Linux-syscall-note) OR BSD-2-Clause) 21 ((GPL-2.0 WITH Linux-syscall-note) OR BSD-3-Clause) 17 LGPL-2.1+ WITH Linux-syscall-note 15 GPL-1.0+ WITH Linux-syscall-note 14 ((GPL-2.0+ WITH Linux-syscall-note) OR BSD-3-Clause) 5 LGPL-2.0+ WITH Linux-syscall-note 4 LGPL-2.1 WITH Linux-syscall-note 3 ((GPL-2.0 WITH Linux-syscall-note) OR MIT) 3 ((GPL-2.0 WITH Linux-syscall-note) AND MIT) 1 and that resulted in the third patch in this series. - when the two scanners agreed on the detected license(s), that became the concluded license(s). - when there was disagreement between the two scanners (one detected a license but the other didn't, or they both detected different licenses) a manual inspection of the file occurred. - In most cases a manual inspection of the information in the file resulted in a clear resolution of the license that should apply (and which scanner probably needed to revisit its heuristics). - When it was not immediately clear, the license identifier was confirmed with lawyers working with the Linux Foundation. - If there was any question as to the appropriate license identifier, the file was flagged for further research and to be revisited later in time. In total, over 70 hours of logged manual review was done on the spreadsheet to determine the SPDX license identifiers to apply to the source files by Kate, Philippe, Thomas and, in some cases, confirmation by lawyers working with the Linux Foundation. Kate also obtained a third independent scan of the 4.13 code base from FOSSology, and compared selected files where the other two scanners disagreed against that SPDX file, to see if there was new insights. The Windriver scanner is based on an older version of FOSSology in part, so they are related. Thomas did random spot checks in about 500 files from the spreadsheets for the uapi headers and agreed with SPDX license identifier in the files he inspected. For the non-uapi files Thomas did random spot checks in about 15000 files. In initial set of patches against 4.14-rc6, 3 files were found to have copy/paste license identifier errors, and have been fixed to reflect the correct identifier. Additionally Philippe spent 10 hours this week doing a detailed manual inspection and review of the 12,461 patched files from the initial patch version early this week with: - a full scancode scan run, collecting the matched texts, detected license ids and scores - reviewing anything where there was a license detected (about 500+ files) to ensure that the applied SPDX license was correct - reviewing anything where there was no detection but the patch license was not GPL-2.0 WITH Linux-syscall-note to ensure that the applied SPDX license was correct This produced a worksheet with 20 files needing minor correction. This worksheet was then exported into 3 different .csv files for the different types of files to be modified. These .csv files were then reviewed by Greg. Thomas wrote a script to parse the csv files and add the proper SPDX tag to the file, in the format that the file expected. This script was further refined by Greg based on the output to detect more types of files automatically and to distinguish between header and source .c files (which need different comment types.) Finally Greg ran the script using the .csv files to generate the patches. Reviewed-by: Kate Stewart <kstewart@linuxfoundation.org> Reviewed-by: Philippe Ombredanne <pombredanne@nexb.com> Reviewed-by: Thomas Gleixner <tglx@linutronix.de> Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
2017-11-01 17:07:57 +03:00
// SPDX-License-Identifier: GPL-2.0
/*
* sysctl_net_ipv6.c: sysctl interface to net IPV6 subsystem.
*
* Changes:
* YOSHIFUJI Hideaki @USAGI: added icmp sysctl table.
*/
#include <linux/mm.h>
#include <linux/sysctl.h>
#include <linux/in6.h>
#include <linux/ipv6.h>
include cleanup: Update gfp.h and slab.h includes to prepare for breaking implicit slab.h inclusion from percpu.h percpu.h is included by sched.h and module.h and thus ends up being included when building most .c files. percpu.h includes slab.h which in turn includes gfp.h making everything defined by the two files universally available and complicating inclusion dependencies. percpu.h -> slab.h dependency is about to be removed. Prepare for this change by updating users of gfp and slab facilities include those headers directly instead of assuming availability. As this conversion needs to touch large number of source files, the following script is used as the basis of conversion. http://userweb.kernel.org/~tj/misc/slabh-sweep.py The script does the followings. * Scan files for gfp and slab usages and update includes such that only the necessary includes are there. ie. if only gfp is used, gfp.h, if slab is used, slab.h. * When the script inserts a new include, it looks at the include blocks and try to put the new include such that its order conforms to its surrounding. It's put in the include block which contains core kernel includes, in the same order that the rest are ordered - alphabetical, Christmas tree, rev-Xmas-tree or at the end if there doesn't seem to be any matching order. * If the script can't find a place to put a new include (mostly because the file doesn't have fitting include block), it prints out an error message indicating which .h file needs to be added to the file. The conversion was done in the following steps. 1. The initial automatic conversion of all .c files updated slightly over 4000 files, deleting around 700 includes and adding ~480 gfp.h and ~3000 slab.h inclusions. The script emitted errors for ~400 files. 2. Each error was manually checked. Some didn't need the inclusion, some needed manual addition while adding it to implementation .h or embedding .c file was more appropriate for others. This step added inclusions to around 150 files. 3. The script was run again and the output was compared to the edits from #2 to make sure no file was left behind. 4. Several build tests were done and a couple of problems were fixed. e.g. lib/decompress_*.c used malloc/free() wrappers around slab APIs requiring slab.h to be added manually. 5. The script was run on all .h files but without automatically editing them as sprinkling gfp.h and slab.h inclusions around .h files could easily lead to inclusion dependency hell. Most gfp.h inclusion directives were ignored as stuff from gfp.h was usually wildly available and often used in preprocessor macros. Each slab.h inclusion directive was examined and added manually as necessary. 6. percpu.h was updated not to include slab.h. 7. Build test were done on the following configurations and failures were fixed. CONFIG_GCOV_KERNEL was turned off for all tests (as my distributed build env didn't work with gcov compiles) and a few more options had to be turned off depending on archs to make things build (like ipr on powerpc/64 which failed due to missing writeq). * x86 and x86_64 UP and SMP allmodconfig and a custom test config. * powerpc and powerpc64 SMP allmodconfig * sparc and sparc64 SMP allmodconfig * ia64 SMP allmodconfig * s390 SMP allmodconfig * alpha SMP allmodconfig * um on x86_64 SMP allmodconfig 8. percpu.h modifications were reverted so that it could be applied as a separate patch and serve as bisection point. Given the fact that I had only a couple of failures from tests on step 6, I'm fairly confident about the coverage of this conversion patch. If there is a breakage, it's likely to be something in one of the arch headers which should be easily discoverable easily on most builds of the specific arch. Signed-off-by: Tejun Heo <tj@kernel.org> Guess-its-ok-by: Christoph Lameter <cl@linux-foundation.org> Cc: Ingo Molnar <mingo@redhat.com> Cc: Lee Schermerhorn <Lee.Schermerhorn@hp.com>
2010-03-24 11:04:11 +03:00
#include <linux/slab.h>
#include <linux/export.h>
#include <net/ndisc.h>
#include <net/ipv6.h>
#include <net/addrconf.h>
#include <net/inet_frag.h>
#include <net/netevent.h>
#ifdef CONFIG_NETLABEL
#include <net/calipso.h>
#endif
static int flowlabel_reflect_max = 0x7;
static int auto_flowlabels_min;
static int auto_flowlabels_max = IP6_AUTO_FLOW_LABEL_MAX;
static int proc_rt6_multipath_hash_policy(struct ctl_table *table, int write,
void *buffer, size_t *lenp, loff_t *ppos)
{
struct net *net;
int ret;
net = container_of(table->data, struct net,
ipv6.sysctl.multipath_hash_policy);
ret = proc_dointvec_minmax(table, write, buffer, lenp, ppos);
if (write && ret == 0)
call_netevent_notifiers(NETEVENT_IPV6_MPATH_HASH_UPDATE, net);
return ret;
}
static struct ctl_table ipv6_table_template[] = {
{
.procname = "bindv6only",
.data = &init_net.ipv6.sysctl.bindv6only,
.maxlen = sizeof(int),
.mode = 0644,
.proc_handler = proc_dointvec
},
{
.procname = "anycast_src_echo_reply",
.data = &init_net.ipv6.sysctl.anycast_src_echo_reply,
.maxlen = sizeof(int),
.mode = 0644,
.proc_handler = proc_dointvec
},
{
.procname = "flowlabel_consistency",
.data = &init_net.ipv6.sysctl.flowlabel_consistency,
.maxlen = sizeof(int),
.mode = 0644,
.proc_handler = proc_dointvec
},
ipv6: Implement automatic flow label generation on transmit Automatically generate flow labels for IPv6 packets on transmit. The flow label is computed based on skb_get_hash. The flow label will only automatically be set when it is zero otherwise (i.e. flow label manager hasn't set one). This supports the transmit side functionality of RFC 6438. Added an IPv6 sysctl auto_flowlabels to enable/disable this behavior system wide, and added IPV6_AUTOFLOWLABEL socket option to enable this functionality per socket. By default, auto flowlabels are disabled to avoid possible conflicts with flow label manager, however if this feature proves useful we may want to enable it by default. It should also be noted that FreeBSD has already implemented automatic flow labels (including the sysctl and socket option). In FreeBSD, automatic flow labels default to enabled. Performance impact: Running super_netperf with 200 flows for TCP_RR and UDP_RR for IPv6. Note that in UDP case, __skb_get_hash will be called for every packet with explains slight regression. In the TCP case the hash is saved in the socket so there is no regression. Automatic flow labels disabled: TCP_RR: 86.53% CPU utilization 127/195/322 90/95/99% latencies 1.40498e+06 tps UDP_RR: 90.70% CPU utilization 118/168/243 90/95/99% latencies 1.50309e+06 tps Automatic flow labels enabled: TCP_RR: 85.90% CPU utilization 128/199/337 90/95/99% latencies 1.40051e+06 UDP_RR 92.61% CPU utilization 115/164/236 90/95/99% latencies 1.4687e+06 Signed-off-by: Tom Herbert <therbert@google.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2014-07-02 08:33:10 +04:00
{
.procname = "auto_flowlabels",
.data = &init_net.ipv6.sysctl.auto_flowlabels,
.maxlen = sizeof(int),
.mode = 0644,
.proc_handler = proc_dointvec_minmax,
.extra1 = &auto_flowlabels_min,
.extra2 = &auto_flowlabels_max
ipv6: Implement automatic flow label generation on transmit Automatically generate flow labels for IPv6 packets on transmit. The flow label is computed based on skb_get_hash. The flow label will only automatically be set when it is zero otherwise (i.e. flow label manager hasn't set one). This supports the transmit side functionality of RFC 6438. Added an IPv6 sysctl auto_flowlabels to enable/disable this behavior system wide, and added IPV6_AUTOFLOWLABEL socket option to enable this functionality per socket. By default, auto flowlabels are disabled to avoid possible conflicts with flow label manager, however if this feature proves useful we may want to enable it by default. It should also be noted that FreeBSD has already implemented automatic flow labels (including the sysctl and socket option). In FreeBSD, automatic flow labels default to enabled. Performance impact: Running super_netperf with 200 flows for TCP_RR and UDP_RR for IPv6. Note that in UDP case, __skb_get_hash will be called for every packet with explains slight regression. In the TCP case the hash is saved in the socket so there is no regression. Automatic flow labels disabled: TCP_RR: 86.53% CPU utilization 127/195/322 90/95/99% latencies 1.40498e+06 tps UDP_RR: 90.70% CPU utilization 118/168/243 90/95/99% latencies 1.50309e+06 tps Automatic flow labels enabled: TCP_RR: 85.90% CPU utilization 128/199/337 90/95/99% latencies 1.40051e+06 UDP_RR 92.61% CPU utilization 115/164/236 90/95/99% latencies 1.4687e+06 Signed-off-by: Tom Herbert <therbert@google.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2014-07-02 08:33:10 +04:00
},
{
.procname = "fwmark_reflect",
.data = &init_net.ipv6.sysctl.fwmark_reflect,
.maxlen = sizeof(int),
.mode = 0644,
.proc_handler = proc_dointvec
},
{
.procname = "idgen_retries",
.data = &init_net.ipv6.sysctl.idgen_retries,
.maxlen = sizeof(int),
.mode = 0644,
.proc_handler = proc_dointvec,
},
{
.procname = "idgen_delay",
.data = &init_net.ipv6.sysctl.idgen_delay,
.maxlen = sizeof(int),
.mode = 0644,
.proc_handler = proc_dointvec_jiffies,
},
ipv6: Flow label state ranges This patch divides the IPv6 flow label space into two ranges: 0-7ffff is reserved for flow label manager, 80000-fffff will be used for creating auto flow labels (per RFC6438). This only affects how labels are set on transmit, it does not affect receive. This range split can be disbaled by systcl. Background: IPv6 flow labels have been an unmitigated disappointment thus far in the lifetime of IPv6. Support in HW devices to use them for ECMP is lacking, and OSes don't turn them on by default. If we had these we could get much better hashing in IPv6 networks without resorting to DPI, possibly eliminating some of the motivations to to define new encaps in UDP just for getting ECMP. Unfortunately, the initial specfications of IPv6 did not clarify how they are to be used. There has always been a vague concept that these can be used for ECMP, flow hashing, etc. and we do now have a good standard how to this in RFC6438. The problem is that flow labels can be either stateful or stateless (as in RFC6438), and we are presented with the possibility that a stateless label may collide with a stateful one. Attempts to split the flow label space were rejected in IETF. When we added support in Linux for RFC6438, we could not turn on flow labels by default due to this conflict. This patch splits the flow label space and should give us a path to enabling auto flow labels by default for all IPv6 packets. This is an API change so we need to consider compatibility with existing deployment. The stateful range is chosen to be the lower values in hopes that most uses would have chosen small numbers. Once we resolve the stateless/stateful issue, we can proceed to look at enabling RFC6438 flow labels by default (starting with scaled testing). Signed-off-by: Tom Herbert <tom@herbertland.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2015-04-30 01:33:21 +03:00
{
.procname = "flowlabel_state_ranges",
.data = &init_net.ipv6.sysctl.flowlabel_state_ranges,
.maxlen = sizeof(int),
.mode = 0644,
.proc_handler = proc_dointvec
},
{
.procname = "ip_nonlocal_bind",
.data = &init_net.ipv6.sysctl.ip_nonlocal_bind,
.maxlen = sizeof(int),
.mode = 0644,
.proc_handler = proc_dointvec
},
{
.procname = "flowlabel_reflect",
.data = &init_net.ipv6.sysctl.flowlabel_reflect,
.maxlen = sizeof(int),
.mode = 0644,
.proc_handler = proc_dointvec_minmax,
proc/sysctl: add shared variables for range check In the sysctl code the proc_dointvec_minmax() function is often used to validate the user supplied value between an allowed range. This function uses the extra1 and extra2 members from struct ctl_table as minimum and maximum allowed value. On sysctl handler declaration, in every source file there are some readonly variables containing just an integer which address is assigned to the extra1 and extra2 members, so the sysctl range is enforced. The special values 0, 1 and INT_MAX are very often used as range boundary, leading duplication of variables like zero=0, one=1, int_max=INT_MAX in different source files: $ git grep -E '\.extra[12].*&(zero|one|int_max)' |wc -l 248 Add a const int array containing the most commonly used values, some macros to refer more easily to the correct array member, and use them instead of creating a local one for every object file. This is the bloat-o-meter output comparing the old and new binary compiled with the default Fedora config: # scripts/bloat-o-meter -d vmlinux.o.old vmlinux.o add/remove: 2/2 grow/shrink: 0/2 up/down: 24/-188 (-164) Data old new delta sysctl_vals - 12 +12 __kstrtab_sysctl_vals - 12 +12 max 14 10 -4 int_max 16 - -16 one 68 - -68 zero 128 28 -100 Total: Before=20583249, After=20583085, chg -0.00% [mcroce@redhat.com: tipc: remove two unused variables] Link: http://lkml.kernel.org/r/20190530091952.4108-1-mcroce@redhat.com [akpm@linux-foundation.org: fix net/ipv6/sysctl_net_ipv6.c] [arnd@arndb.de: proc/sysctl: make firmware loader table conditional] Link: http://lkml.kernel.org/r/20190617130014.1713870-1-arnd@arndb.de [akpm@linux-foundation.org: fix fs/eventpoll.c] Link: http://lkml.kernel.org/r/20190430180111.10688-1-mcroce@redhat.com Signed-off-by: Matteo Croce <mcroce@redhat.com> Signed-off-by: Arnd Bergmann <arnd@arndb.de> Acked-by: Kees Cook <keescook@chromium.org> Reviewed-by: Aaron Tomlin <atomlin@redhat.com> Cc: Matthew Wilcox <willy@infradead.org> Cc: Stephen Rothwell <sfr@canb.auug.org.au> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2019-07-19 01:58:50 +03:00
.extra1 = SYSCTL_ZERO,
.extra2 = &flowlabel_reflect_max,
},
ipv6: Implement limits on Hop-by-Hop and Destination options RFC 8200 (IPv6) defines Hop-by-Hop options and Destination options extension headers. Both of these carry a list of TLVs which is only limited by the maximum length of the extension header (2048 bytes). By the spec a host must process all the TLVs in these options, however these could be used as a fairly obvious denial of service attack. I think this could in fact be a significant DOS vector on the Internet, one mitigating factor might be that many FWs drop all packets with EH (and obviously this is only IPv6) so an Internet wide attack might not be so effective (yet!). By my calculation, the worse case packet with TLVs in a standard 1500 byte MTU packet that would be processed by the stack contains 1282 invidual TLVs (including pad TLVS) or 724 two byte TLVs. I wrote a quick test program that floods a whole bunch of these packets to a host and sure enough there is substantial time spent in ip6_parse_tlv. These packets contain nothing but unknown TLVS (that are ignored), TLV padding, and bogus UDP header with zero payload length. 25.38% [kernel] [k] __fib6_clean_all 21.63% [kernel] [k] ip6_parse_tlv 4.21% [kernel] [k] __local_bh_enable_ip 2.18% [kernel] [k] ip6_pol_route.isra.39 1.98% [kernel] [k] fib6_walk_continue 1.88% [kernel] [k] _raw_write_lock_bh 1.65% [kernel] [k] dst_release This patch adds configurable limits to Destination and Hop-by-Hop options. There are three limits that may be set: - Limit the number of options in a Hop-by-Hop or Destination options extension header. - Limit the byte length of a Hop-by-Hop or Destination options extension header. - Disallow unrecognized options in a Hop-by-Hop or Destination options extension header. The limits are set in corresponding sysctls: ipv6.sysctl.max_dst_opts_cnt ipv6.sysctl.max_hbh_opts_cnt ipv6.sysctl.max_dst_opts_len ipv6.sysctl.max_hbh_opts_len If a max_*_opts_cnt is less than zero then unknown TLVs are disallowed. The number of known TLVs that are allowed is the absolute value of this number. If a limit is exceeded when processing an extension header the packet is dropped. Default values are set to 8 for options counts, and set to INT_MAX for maximum length. Note the choice to limit options to 8 is an arbitrary guess (roughly based on the fact that the stack supports three HBH options and just one destination option). These limits have being proposed in draft-ietf-6man-rfc6434-bis. Tested (by Martin Lau) I tested out 1 thread (i.e. one raw_udp process). I changed the net.ipv6.max_dst_(opts|hbh)_number between 8 to 2048. With sysctls setting to 2048, the softirq% is packed to 100%. With 8, the softirq% is almost unnoticable from mpstat. v2; - Code and documention cleanup. - Change references of RFC2460 to be RFC8200. - Add reference to RFC6434-bis where the limits will be in standard. Signed-off-by: Tom Herbert <tom@quantonium.net> Signed-off-by: David S. Miller <davem@davemloft.net>
2017-10-31 00:16:00 +03:00
{
.procname = "max_dst_opts_number",
.data = &init_net.ipv6.sysctl.max_dst_opts_cnt,
.maxlen = sizeof(int),
.mode = 0644,
.proc_handler = proc_dointvec
},
{
.procname = "max_hbh_opts_number",
.data = &init_net.ipv6.sysctl.max_hbh_opts_cnt,
.maxlen = sizeof(int),
.mode = 0644,
.proc_handler = proc_dointvec
},
{
.procname = "max_dst_opts_length",
.data = &init_net.ipv6.sysctl.max_dst_opts_len,
.maxlen = sizeof(int),
.mode = 0644,
.proc_handler = proc_dointvec
},
{
.procname = "max_hbh_length",
.data = &init_net.ipv6.sysctl.max_hbh_opts_len,
.maxlen = sizeof(int),
.mode = 0644,
.proc_handler = proc_dointvec
},
{
.procname = "fib_multipath_hash_policy",
.data = &init_net.ipv6.sysctl.multipath_hash_policy,
.maxlen = sizeof(int),
.mode = 0644,
.proc_handler = proc_rt6_multipath_hash_policy,
proc/sysctl: add shared variables for range check In the sysctl code the proc_dointvec_minmax() function is often used to validate the user supplied value between an allowed range. This function uses the extra1 and extra2 members from struct ctl_table as minimum and maximum allowed value. On sysctl handler declaration, in every source file there are some readonly variables containing just an integer which address is assigned to the extra1 and extra2 members, so the sysctl range is enforced. The special values 0, 1 and INT_MAX are very often used as range boundary, leading duplication of variables like zero=0, one=1, int_max=INT_MAX in different source files: $ git grep -E '\.extra[12].*&(zero|one|int_max)' |wc -l 248 Add a const int array containing the most commonly used values, some macros to refer more easily to the correct array member, and use them instead of creating a local one for every object file. This is the bloat-o-meter output comparing the old and new binary compiled with the default Fedora config: # scripts/bloat-o-meter -d vmlinux.o.old vmlinux.o add/remove: 2/2 grow/shrink: 0/2 up/down: 24/-188 (-164) Data old new delta sysctl_vals - 12 +12 __kstrtab_sysctl_vals - 12 +12 max 14 10 -4 int_max 16 - -16 one 68 - -68 zero 128 28 -100 Total: Before=20583249, After=20583085, chg -0.00% [mcroce@redhat.com: tipc: remove two unused variables] Link: http://lkml.kernel.org/r/20190530091952.4108-1-mcroce@redhat.com [akpm@linux-foundation.org: fix net/ipv6/sysctl_net_ipv6.c] [arnd@arndb.de: proc/sysctl: make firmware loader table conditional] Link: http://lkml.kernel.org/r/20190617130014.1713870-1-arnd@arndb.de [akpm@linux-foundation.org: fix fs/eventpoll.c] Link: http://lkml.kernel.org/r/20190430180111.10688-1-mcroce@redhat.com Signed-off-by: Matteo Croce <mcroce@redhat.com> Signed-off-by: Arnd Bergmann <arnd@arndb.de> Acked-by: Kees Cook <keescook@chromium.org> Reviewed-by: Aaron Tomlin <atomlin@redhat.com> Cc: Matthew Wilcox <willy@infradead.org> Cc: Stephen Rothwell <sfr@canb.auug.org.au> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2019-07-19 01:58:50 +03:00
.extra1 = SYSCTL_ZERO,
.extra2 = SYSCTL_ONE,
},
ipv6: sr: Compute flowlabel for outer IPv6 header of seg6 encap mode ECMP (equal-cost multipath) hashes are typically computed on the packets' 5-tuple(src IP, dst IP, src port, dst port, L4 proto). For encapsulated packets, the L4 data is not readily available and ECMP hashing will often revert to (src IP, dst IP). This will lead to traffic polarization on a single ECMP path, causing congestion and waste of network capacity. In IPv6, the 20-bit flow label field is also used as part of the ECMP hash. In the lack of L4 data, the hashing will be on (src IP, dst IP, flow label). Having a non-zero flow label is thus important for proper traffic load balancing when L4 data is unavailable (i.e., when packets are encapsulated). Currently, the seg6_do_srh_encap() function extracts the original packet's flow label and set it as the outer IPv6 flow label. There are two issues with this behaviour: a) There is no guarantee that the inner flow label is set by the source. b) If the original packet is not IPv6, the flow label will be set to zero (e.g., IPv4 or L2 encap). This patch adds a function, named seg6_make_flowlabel(), that computes a flow label from a given skb. It supports IPv6, IPv4 and L2 payloads, and leverages the per namespace 'seg6_flowlabel" sysctl value. The currently support behaviours are as follows: -1 set flowlabel to zero. 0 copy flowlabel from Inner paceket in case of Inner IPv6 (Set flowlabel to 0 in case IPv4/L2) 1 Compute the flowlabel using seg6_make_flowlabel() This patch has been tested for IPv6, IPv4, and L2 traffic. Signed-off-by: Ahmed Abdelsalam <amsalam20@gmail.com> Acked-by: David Lebrun <dlebrun@google.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2018-04-24 21:23:16 +03:00
{
.procname = "seg6_flowlabel",
.data = &init_net.ipv6.sysctl.seg6_flowlabel,
.maxlen = sizeof(int),
.mode = 0644,
.proc_handler = proc_dointvec
},
{ }
};
static struct ctl_table ipv6_rotable[] = {
{
.procname = "mld_max_msf",
.data = &sysctl_mld_max_msf,
.maxlen = sizeof(int),
.mode = 0644,
.proc_handler = proc_dointvec
},
{
.procname = "mld_qrv",
.data = &sysctl_mld_qrv,
.maxlen = sizeof(int),
.mode = 0644,
.proc_handler = proc_dointvec_minmax,
proc/sysctl: add shared variables for range check In the sysctl code the proc_dointvec_minmax() function is often used to validate the user supplied value between an allowed range. This function uses the extra1 and extra2 members from struct ctl_table as minimum and maximum allowed value. On sysctl handler declaration, in every source file there are some readonly variables containing just an integer which address is assigned to the extra1 and extra2 members, so the sysctl range is enforced. The special values 0, 1 and INT_MAX are very often used as range boundary, leading duplication of variables like zero=0, one=1, int_max=INT_MAX in different source files: $ git grep -E '\.extra[12].*&(zero|one|int_max)' |wc -l 248 Add a const int array containing the most commonly used values, some macros to refer more easily to the correct array member, and use them instead of creating a local one for every object file. This is the bloat-o-meter output comparing the old and new binary compiled with the default Fedora config: # scripts/bloat-o-meter -d vmlinux.o.old vmlinux.o add/remove: 2/2 grow/shrink: 0/2 up/down: 24/-188 (-164) Data old new delta sysctl_vals - 12 +12 __kstrtab_sysctl_vals - 12 +12 max 14 10 -4 int_max 16 - -16 one 68 - -68 zero 128 28 -100 Total: Before=20583249, After=20583085, chg -0.00% [mcroce@redhat.com: tipc: remove two unused variables] Link: http://lkml.kernel.org/r/20190530091952.4108-1-mcroce@redhat.com [akpm@linux-foundation.org: fix net/ipv6/sysctl_net_ipv6.c] [arnd@arndb.de: proc/sysctl: make firmware loader table conditional] Link: http://lkml.kernel.org/r/20190617130014.1713870-1-arnd@arndb.de [akpm@linux-foundation.org: fix fs/eventpoll.c] Link: http://lkml.kernel.org/r/20190430180111.10688-1-mcroce@redhat.com Signed-off-by: Matteo Croce <mcroce@redhat.com> Signed-off-by: Arnd Bergmann <arnd@arndb.de> Acked-by: Kees Cook <keescook@chromium.org> Reviewed-by: Aaron Tomlin <atomlin@redhat.com> Cc: Matthew Wilcox <willy@infradead.org> Cc: Stephen Rothwell <sfr@canb.auug.org.au> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2019-07-19 01:58:50 +03:00
.extra1 = SYSCTL_ONE
},
#ifdef CONFIG_NETLABEL
{
.procname = "calipso_cache_enable",
.data = &calipso_cache_enabled,
.maxlen = sizeof(int),
.mode = 0644,
.proc_handler = proc_dointvec,
},
{
.procname = "calipso_cache_bucket_size",
.data = &calipso_cache_bucketsize,
.maxlen = sizeof(int),
.mode = 0644,
.proc_handler = proc_dointvec,
},
#endif /* CONFIG_NETLABEL */
{ }
};
static int __net_init ipv6_sysctl_net_init(struct net *net)
{
struct ctl_table *ipv6_table;
struct ctl_table *ipv6_route_table;
struct ctl_table *ipv6_icmp_table;
int err, i;
err = -ENOMEM;
ipv6_table = kmemdup(ipv6_table_template, sizeof(ipv6_table_template),
GFP_KERNEL);
if (!ipv6_table)
goto out;
/* Update the variables to point into the current struct net */
for (i = 0; i < ARRAY_SIZE(ipv6_table_template) - 1; i++)
ipv6_table[i].data += (void *)net - (void *)&init_net;
ipv6_route_table = ipv6_route_sysctl_init(net);
if (!ipv6_route_table)
goto out_ipv6_table;
ipv6_icmp_table = ipv6_icmp_sysctl_init(net);
if (!ipv6_icmp_table)
goto out_ipv6_route_table;
net->ipv6.sysctl.hdr = register_net_sysctl(net, "net/ipv6", ipv6_table);
if (!net->ipv6.sysctl.hdr)
goto out_ipv6_icmp_table;
net->ipv6.sysctl.route_hdr =
register_net_sysctl(net, "net/ipv6/route", ipv6_route_table);
if (!net->ipv6.sysctl.route_hdr)
goto out_unregister_ipv6_table;
net->ipv6.sysctl.icmp_hdr =
register_net_sysctl(net, "net/ipv6/icmp", ipv6_icmp_table);
if (!net->ipv6.sysctl.icmp_hdr)
goto out_unregister_route_table;
err = 0;
out:
return err;
out_unregister_route_table:
unregister_net_sysctl_table(net->ipv6.sysctl.route_hdr);
out_unregister_ipv6_table:
unregister_net_sysctl_table(net->ipv6.sysctl.hdr);
out_ipv6_icmp_table:
kfree(ipv6_icmp_table);
out_ipv6_route_table:
kfree(ipv6_route_table);
out_ipv6_table:
kfree(ipv6_table);
goto out;
}
static void __net_exit ipv6_sysctl_net_exit(struct net *net)
{
struct ctl_table *ipv6_table;
struct ctl_table *ipv6_route_table;
struct ctl_table *ipv6_icmp_table;
ipv6_table = net->ipv6.sysctl.hdr->ctl_table_arg;
ipv6_route_table = net->ipv6.sysctl.route_hdr->ctl_table_arg;
ipv6_icmp_table = net->ipv6.sysctl.icmp_hdr->ctl_table_arg;
unregister_net_sysctl_table(net->ipv6.sysctl.icmp_hdr);
unregister_net_sysctl_table(net->ipv6.sysctl.route_hdr);
unregister_net_sysctl_table(net->ipv6.sysctl.hdr);
kfree(ipv6_table);
kfree(ipv6_route_table);
kfree(ipv6_icmp_table);
}
static struct pernet_operations ipv6_sysctl_net_ops = {
.init = ipv6_sysctl_net_init,
.exit = ipv6_sysctl_net_exit,
};
static struct ctl_table_header *ip6_header;
int ipv6_sysctl_register(void)
{
int err = -ENOMEM;
ip6_header = register_net_sysctl(&init_net, "net/ipv6", ipv6_rotable);
if (!ip6_header)
goto out;
err = register_pernet_subsys(&ipv6_sysctl_net_ops);
if (err)
goto err_pernet;
out:
return err;
err_pernet:
unregister_net_sysctl_table(ip6_header);
goto out;
}
void ipv6_sysctl_unregister(void)
{
unregister_net_sysctl_table(ip6_header);
unregister_pernet_subsys(&ipv6_sysctl_net_ops);
}